© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199428
    Prev
    Next
    INDEX
    Explanations

    fat-rich sauce

    np_acts-logits-general · gemini-2.5-flash-lite

    direct customer support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biofilms
    0.50
     diferite
    0.47
     przechowy
    0.47
     investigación
    0.46
     Sitio
    0.46
     Zellen
    0.46
    倫
    0.46
     almacenar
    0.45
     trữ
    0.45
     stör
    0.45
    POSITIVE LOGITS
    ount
    0.52
    ome
    0.50
    delete
    0.49
    ali
    0.48
    parent
    0.47
    m
    0.46
    omely
    0.46
    api
    0.45
    <<<<
    0.45
    ih
    0.45
    Activations Density 0.001%

    No Known Activations